INDEX

Explanations

mathematical operations and expressions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

"both" followed by another word

np_acts-logits-general · gemini-2.0-flash

multiplying, dividing, both sides, collect terms

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 écoulé

-0.54

Super

-0.45

 agrí

-0.44

 παρά

-0.44

้ม

-0.43

 savoir

-0.42

toja

-0.41

 indican

-0.41

ondata

-0.41

visit

-0.40

POSITIVE LOGITS

 propOrder

0.63

 surla

0.63

TagMode

0.63

mybatisplus

0.63

ViewFeatures

0.62

RHS

0.60

 MenuView

0.59

 iNdEx

0.59

 nakalista

0.58

HtmlAttribute

0.58

Activations Density 0.881%

mathematical operations and expressions

"both" followed by another word

multiplying, dividing, both sides, collect terms

No Comments

No Known Activations